artificial intelligence is constantly advancing and efforts to promote digital independence and linguistic diversity have taken an important step forward with the creation of ai/blog/viking-7b-13b-33b-sailing-the-nordic-seas-of-multilinguality”>Viking, A state-of-the-art language model. Developed by Silo ai, Europe's largest private ai lab, in collaboration with the TurkuNLP research group at the University of Turku and HPLT, Viking is designed to serve Nordic languages, as well as English and programming languages. . The release of its first checkpoints marks a crucial milestone in making European language models more accessible.
Viking is the latest and improved version of Silo ai's previous LLM model,ai/blog/europes-open-language-model-poro-a-milestone-for-european-ai-and-low-resource-languages”> “ball”. The Viking architecture has been modernized and language support has been expanded to include multiple languages such as Danish, English, Finnish, Norwegian, Icelandic, Swedish and several programming languages. Viking comes in three different models: viking 7b, 13Band 33B – which demonstrate Silo ai's dedication to improving Europe's digital infrastructure, promoting linguistic diversity and ensuring that technology brings people together rather than creating cultural barriers.
A technological and cultural bridge
Viking's development is emblematic of Europe's broader strategy to strengthen its digital sovereignty while embracing linguistic diversity. By leveraging the latest advances in multilingual LLMs, Silo ai and TurkuNLP aim to create tools that are linguistically inclusive and culturally sensitive. Viking is specifically designed to perform exceptionally well in languages that typically receive less attention in the global ai race, thus providing a platform for innovation and communication within and beyond the Nordic region.
Performance
Viking's performance is quite impressive, especially when it comes to low-resource languages. Based on initial evaluations after being trained with 1 billion tokens, Viking has been found to outperform other open models in these languages while maintaining its efficiency in English and programming languages. This achievement highlights the effectiveness of Viking's approach in training multilingual models and its technological advancement to address the complexities of multilingualism.
Architecture
Viking's architecture is inspired by successful models like Llama 2, which includes features like flash attention, spin embedding, and clustered query attention. It supports a sequence length of up to 4000 and is backed by a data set of 2 billion tokens. The data covers Nordic languages and a variety of programming languages. This demonstrates significant progress towards the creation of a multilingual and multifunctional LLM.
Open access and ethical considerations
Viking is published under the Apache 2.0 license, making it freely available for research and commercial purposes. Although Viking research checkpoints are useful for academic and industrial research, Silo ai recommends additional training and adjustments before deployment in production environments.
Key takeaways
- democratize multilingualism: Viking represents a significant effort to bring linguistic diversity to the forefront of ai development, particularly for Nordic languages.
- Technological innovation: With a state-of-the-art architecture and extensive training data, Viking shows superior performance in understanding and generating multilingual content.
- Cultural sensitivity: The development of the model emphasizes the importance of creating technology that respects and incorporates local values and cultures.
- Open access: Viking is freely available under the Apache 2.0 license, fostering innovation across multiple sectors by providing access to a high-quality multilingual LLM.
- European digital sovereignty: The launch of Viking aligns with Europe's strategy to improve its digital infrastructure and autonomy, positioning it as a leader in the global ai landscape.
Asif Razzaq is the CEO of Marktechpost Media Inc.. As a visionary entrepreneur and engineer, Asif is committed to harnessing the potential of artificial intelligence for social good. His most recent endeavor is the launch of an ai media platform, Marktechpost, which stands out for its in-depth coverage of machine learning and deep learning news that is technically sound and easily understandable to a wide audience. The platform has more than 2 million monthly visits, which illustrates its popularity among the public.
